add-voice-transcription

Transcribe WhatsApp voice messages into text using OpenAI Whisper.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/nrupala/nanoclaw --skill add-voice-transcription-nrupala
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/nrupala/nanoclaw/tree/main/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/nrupala/nanoclaw --skill add-voice-transcription-nrupala

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automatically transcribes WhatsApp voice messages into text so NanoClaw agents can understand and respond without listening to audio.

Core Features & Use Cases

  • Whisper-based voice transcription for WhatsApp messages
  • Seamless integration with the WhatsApp channel and agent workflow
  • Use Case: When a user sends a voice note, the agent receives a transcript like [Voice: <transcript>], enabling timely replies.

Quick Start

Merge this skill into your WhatsApp workflow and provide your OpenAI API key to enable transcription.

Frequently Asked Questions about add-voice-transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe WhatsApp voice messages into text for my agent?

OpenAI Whisper is used to transcribe WhatsApp voice notes by sending the audio through the Whisper API, which returns a text transcript. This transcript is formatted as [Voice: <transcript>] and passed directly to the agent workflow for processing.

What do I need to set up Whisper transcription for WhatsApp chats?

Setting up Whisper voice transcription requires a valid OpenAI Whisper API key, a configured WhatsApp channel, and an environment to run the transcription module. Once configured, it automatically converts short and long voice notes into readable text.

Can my agent process long WhatsApp voice notes or is there a message length limit?

The voice transcription supports both short and long WhatsApp voice notes, converting them entirely into readable text transcripts. This ensures your agent receives the full context of the audio message regardless of its length for accurate processing.

How are transcribed voice notes formatted for the agent to read?

Transcribed voice notes are formatted as [Voice: <transcript>], displaying the readable text directly within the WhatsApp chat interface. This specific formatting ensures the agent recognizes the transcribed content and can process it seamlessly.

Does this voice transcription approach work without an OpenAI API key?

No, a valid OpenAI Whisper API key is strictly required to enable voice transcription for WhatsApp messages. The transcription module relies on the Whisper API to convert the audio input into text before the agent can process it.